The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to generate HTML output, creating a potential surface for indirect prompt injection or cross-site scripting if the source material contains malicious content.
Ingestion points: SKILL.md indicates the agent reads conversation history, project instructions, and supplied plans.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined in the skill body.
Capability inventory: The skill is capable of generating and returning a self-contained HTML file.
Sanitization: The instructions do not specify sanitization or escaping of the input data before it is rendered into the HTML document, although they do advise avoiding external services.
[EXTERNAL_DOWNLOADS]: Metadata in the mirror file references an external GitHub repository for source tracking.
Evidence: MIRROR.md lists https://github.com/plannotator/effective-html.git as the source repository. This is used for attribution and documentation of the skill's origin.

effective-html-plan